Thesis Details
Detekce a analýza narušitelů ve sledované oblasti
The aim of this thesis is to create an internet application for detection and analysis of violators in the monitored area. Such an application then can be used for automated processing of records from security cameras or other captured videos from the guarded area. The first part of the work is focused on the theory of neural networks for object detection and classification in the image and recognition of people by their face. The next part describes used technologies for application development. The result is a client-server application with the possibility of configuration of processing, which allows detection of violators, identification of persons, object tracking and counting, path drawing, definition of the monitored area, usage of own detector, etc. Processed videos at the end can be played, downloaded or together with a list of detected violators shared on the internet via link.
convolutional neural networks, cnn, detection, classification, face recognition, object tracking, image processing, YOLOv3, DeepFace, DeepSORT, internet application, React, Express.js, Socket.io
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Kreslíková Jitka, doc. RNDr., CSc. (DIFS FIT BUT), člen
Mrázek Vojtěch, Ing., Ph.D. (DCSY FIT BUT), člen
Polčák Libor, Ing., Ph.D. (DIFS FIT BUT), člen
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
@mastersthesis{FITMT23849, author = "Jakub Sad\'{i}lek", type = "Master's thesis", title = "Detekce a anal\'{y}za naru\v{s}itel\r{u} ve sledovan\'{e} oblasti", school = "Brno University of Technology, Faculty of Information Technology", year = 2022, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/23849/" }